Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Created this calm lakeshore scene with GPT-6 Astra using Blender. Its geometry is approximately 396,000 unique mesh triangles and 4.91 million evaluated triangles! Enough of the AI-doomer crap! I just keep making bigger ones & put them in loop for some positive relaxation.😊

Derya Unutmaz, MD

341,432 subscribers

10,852 Aufrufe • vor 1 Tag •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

14 Kommentare

Profilbild von lalo 🐧

lalo 🐧vor 1 Tag

you gotta get a VR headset and start building for that, cause this would be perfect to go fishin haha

Profilbild von Derya Unutmaz, MD

Derya Unutmaz, MDvor 1 Tag

hah yes should do that! and I am sure I can code it for the VR :)

Profilbild von lalo 🐧

lalo 🐧vor 1 Tag

pick me up one while you're out there! haha

Profilbild von X Girls

X Girlsvor 1 Tag

When I see videos like this made with Astra, it feels like OpenAI has come full circle on video, but with much better mission alignment. Before, developing Sora independent of the main LLM models was a compute heavy side quest. Whereas now you can use Astra, the core product, to build the scene in Blender and make the video from that.

Profilbild von Vib3Coded

Vib3Codedvor 1 Tag

Honestly, this is the kind of AI content I want to see more of 😌 Just make it bigger and prettier

Profilbild von cryptomanavan ☀️

cryptomanavan ☀️vor 1 Tag

Super cool.

Profilbild von Anthon Noire

Anthon Noirevor 1 Tag

Good to see some positive vibes on AI uses.

Profilbild von Alejandro Maestre | AI

Alejandro Maestre | AIvor 1 Tag

Ese loop de lago con casi 5 millones de triangulos es una locura. Prefiero ver esto que leer otro doompost sobre IA.

Profilbild von Chetan | 3D Websites Daily

Chetan | 3D Websites Dailyvor 1 Tag

Love it ! Am gonna share my lake soon but till then here’s my peace spot

Profilbild von Xzistor LAB

Xzistor LABvor 4 Stunden

Great work! Do you perhaps have some idiot-proof guide for those who would like to do similar? I mean really step-by-step spoon feeding type guidance. Will really appreciate a pointer!

Profilbild von Mr Opp

Mr Oppvor 1 Tag

Now do Dubai..

Profilbild von Derya Unutmaz, MD

Derya Unutmaz, MDvor 1 Tag

that would consume too many tokes, not that rich 😄

Profilbild von Mr Opp

Mr Oppvor 1 Tag

My bad..

Profilbild von renji

renjivor 9 Stunden

This makes me feel so happy.

Ähnliche Videos

This is an example of Germany in settled possession and what's wrong with it. They create wide triangles on both sides which is good as it makes ball circulation and counter pressing easier. However, to make this effective and get the most out the triangles you need movement and rotations within them, just look at England and France for this! Not enough runs in behind, not enough movement and rotations in the final 3rd, lack of wide dribblers (leaving out El Mala, Adeyemi and Schade were mistakes). Not enough patterns of play to advance the ball, no emphasis on manipulating the positioning of the Paraguay backline. Overall not good enough from Germany.

This is an example of Germany in settled possession and what's wrong with it. They create wide triangles on both sides which is good as it makes ball circulation and counter pressing easier. However, to make this effective and get the most out the triangles you need movement and rotations within them, just look at England and France for this! Not enough runs in behind, not enough movement and rotations in the final 3rd, lack of wide dribblers (leaving out El Mala, Adeyemi and Schade were mistakes). Not enough patterns of play to advance the ball, no emphasis on manipulating the positioning of the Paraguay backline. Overall not good enough from Germany.

Dom

19,874 Aufrufe • vor 2 Monaten

I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol. I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while. I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday. Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it. The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :) The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.

I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol. I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while. I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday. Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it. The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :) The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.

ilker

56,896 Aufrufe • vor 5 Tagen

What is really useful is how GPT-6 Astra got better in spatial understanding. I'm still shocked how good it navigates 3D space. Here I gave it Blender MCP and Tripo P2.0 to generate optimized 3D models and put them together, rig and animate. Result is freaking awesome! Doing 3D objects procedurally with Astra is fun, but quality is not compared with what 3D Gen can do. Like you don't ask GPT to draw image with pen when there is GPT Image, same here. And token cost also speaks for it, 3D gen simply cheaper. But the way it assemble thing together, characters and scene, that is shocking ngl. And rigging of course, I have so much hope on it, it is most annoying part of 3d for me lol

What is really useful is how GPT-6 Astra got better in spatial understanding. I'm still shocked how good it navigates 3D space. Here I gave it Blender MCP and Tripo P2.0 to generate optimized 3D models and put them together, rig and animate. Result is freaking awesome! Doing 3D objects procedurally with Astra is fun, but quality is not compared with what 3D Gen can do. Like you don't ask GPT to draw image with pen when there is GPT Image, same here. And token cost also speaks for it, 3D gen simply cheaper. But the way it assemble thing together, characters and scene, that is shocking ngl. And rigging of course, I have so much hope on it, it is most annoying part of 3d for me lol

Stefan 3D AI

19,476 Aufrufe • vor 6 Tagen

OpenAI just released GPT-6 Astra, and OpenAI President Greg Brockman is calling it a generational leap, saying he personally believes it could mark the arrival of AGI. Astra launched on Thursday, September 3rd, 2026, following July's GPT-5.6 solo release. Brockman told reporters, "For me personally, I do think we're there. Directionally, I believe this. I think we're on a path to AGI. The timing I think is kind of uncertain, but we are definitely on a path to AGI." OpenAI executives say Astra moves past the chatbot era, capable of handling end to end work on its own across browsers, spreadsheets, codebases, and enterprise apps without a human in the loop. The model was trained on over 100,000 GPUs at the Stargate site in Texas. Access starts through OpenAI's gated Daybreak Access cybersecurity program for enterprise customers, then rolls out to ChatGPT Plus, Pro, Business, and Enterprise, plus the API and Amazon Web Services over the coming days. Ahead of launch, two models appeared in Codex, GPT-6 Astra and GPT-6 Astra Aeon, with the latter believed to be a higher effort, long horizon variant built for autonomous multi agent work.

OpenAI just released GPT-6 Astra, and OpenAI President Greg Brockman is calling it a generational leap, saying he personally believes it could mark the arrival of AGI. Astra launched on Thursday, September 3rd, 2026, following July's GPT-5.6 solo release. Brockman told reporters, "For me personally, I do think we're there. Directionally, I believe this. I think we're on a path to AGI. The timing I think is kind of uncertain, but we are definitely on a path to AGI." OpenAI executives say Astra moves past the chatbot era, capable of handling end to end work on its own across browsers, spreadsheets, codebases, and enterprise apps without a human in the loop. The model was trained on over 100,000 GPUs at the Stargate site in Texas. Access starts through OpenAI's gated Daybreak Access cybersecurity program for enterprise customers, then rolls out to ChatGPT Plus, Pro, Business, and Enterprise, plus the API and Amazon Web Services over the coming days. Ahead of launch, two models appeared in Codex, GPT-6 Astra and GPT-6 Astra Aeon, with the latter believed to be a higher effort, long horizon variant built for autonomous multi agent work.

AGTP

20,156 Aufrufe • vor 8 Tagen

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

Rahul

353,389 Aufrufe • vor 4 Tagen

Not bad! 2K triangles and a bit of manual cleanup. This was a quick test creating a lowpoly 3D model. Tried Tripo for retopology and it did a good job. It does render some inverted normals though. For this lowpoly model it’s fine but inverted normals are a pain when working on highpoly models. I’m going to test some other options like the remesh tool in Blender sculpting. It’s crazy how this Trellis Texturing node works btw, It understands the geometry very well. Watch the end where I made the worst version of an Axe in Blender and it was able to wrap the texture on that model! I would probably spend a bit more time splitting the image up and generating the main parts separately. Also making any signs readable or just remove them.

Not bad! 2K triangles and a bit of manual cleanup. This was a quick test creating a lowpoly 3D model. Tried Tripo for retopology and it did a good job. It does render some inverted normals though. For this lowpoly model it’s fine but inverted normals are a pain when working on highpoly models. I’m going to test some other options like the remesh tool in Blender sculpting. It’s crazy how this Trellis Texturing node works btw, It understands the geometry very well. Watch the end where I made the worst version of an Axe in Blender and it was able to wrap the texture on that model! I would probably spend a bit more time splitting the image up and generating the main parts separately. Also making any signs readable or just remove them.

Jerome | InsaneUnreal

15,052 Aufrufe • vor 7 Monaten

here is the anti-Zionist song Mohsen made that made them go insane with rage and try to get him cancelled. Thanks to the Simon Wiesenthal Center for their translation of the great lyrics that perfectly describe genocidal Zionists and the Israeli death-cult, a true flock of vultures: The flock of Vultures has arrived again Looks like they have seen new corpses In the name of security very close by They have cut the throats of a nation Their peace is just a facade Just a million soldiers marching by Anywhere there is an inkling of conflict They are ready with their guns drawn Two Triangles they put on top of each other Then they put a new name on the town Two triangles mean Fear and Prison They are the enemies of smiling children They say that they are hiding very close by Their army hanging around optimistically They have occupied the olive groves They have cut flower buds with teeth and nail Wake up people it's already too late Olive groves are already dying Just pray that our Friday night man Can get back our land Two triangles they put together Then they put a new name on the town Two triangles mean fear and prison They are the enemies of the smiling children

here is the anti-Zionist song Mohsen made that made them go insane with rage and try to get him cancelled. Thanks to the Simon Wiesenthal Center for their translation of the great lyrics that perfectly describe genocidal Zionists and the Israeli death-cult, a true flock of vultures: The flock of Vultures has arrived again Looks like they have seen new corpses In the name of security very close by They have cut the throats of a nation Their peace is just a facade Just a million soldiers marching by Anywhere there is an inkling of conflict They are ready with their guns drawn Two Triangles they put on top of each other Then they put a new name on the town Two triangles mean Fear and Prison They are the enemies of smiling children They say that they are hiding very close by Their army hanging around optimistically They have occupied the olive groves They have cut flower buds with teeth and nail Wake up people it's already too late Olive groves are already dying Just pray that our Friday night man Can get back our land Two triangles they put together Then they put a new name on the town Two triangles mean fear and prison They are the enemies of the smiling children

☀️👀

17,979 Aufrufe • vor 5 Monaten

You know I had to do it!! gpt-6-astra (High), one prompt, Terreiro do Paço in Lisbon (Blender, not Three.js!) This one hits home personally 5 years ago, in college, I had a whole course in Computer Graphics. For the final project, every group had to recreate Praça do Comércio / Terreiro do Paço in Blender (our project delivery is in the comments). I wanted to see how Astra would perform. For one-shot, it's pretty damn good. Astra is a beast in Spatial 3d, and Blender is not like Three.js! It's significantly more complex, with a broader range of modeling, materials, lighting, etc. Generational leap (and I will run a few more prompts here)

You know I had to do it!! gpt-6-astra (High), one prompt, Terreiro do Paço in Lisbon (Blender, not Three.js!) This one hits home personally 5 years ago, in college, I had a whole course in Computer Graphics. For the final project, every group had to recreate Praça do Comércio / Terreiro do Paço in Blender (our project delivery is in the comments). I wanted to see how Astra would perform. For one-shot, it's pretty damn good. Astra is a beast in Spatial 3d, and Blender is not like Three.js! It's significantly more complex, with a broader range of modeling, materials, lighting, etc. Generational leap (and I will run a few more prompts here)

Gonçalo Canhoto 🇵🇹

310,788 Aufrufe • vor 6 Tagen

GPT-6 Astra recreated the Palace of Fine arts in Blender. This is favorite building in San Francisco because it was built for the World's Fair in 1914 where the steam locomotive and telephone were showed off. It was a time when technology gave us all a deep sense of optimism for the future. I feel like some of that sense has been lost since, but I hope models like astra can help restore it, and push us towards a more hopeful future.

GPT-6 Astra recreated the Palace of Fine arts in Blender. This is favorite building in San Francisco because it was built for the World's Fair in 1914 where the steam locomotive and telephone were showed off. It was a time when technology gave us all a deep sense of optimism for the future. I feel like some of that sense has been lost since, but I hope models like astra can help restore it, and push us towards a more hopeful future.

Sharif Shameem

2,598,395 Aufrufe • vor 8 Tagen

Asmongold says to never forget the anti AI people in video about AI & GPT-6 Astra "If you're not using these tools and other people are, they're gonna beat you and then people are gonna choose the winner..think about how many things now are determined or done partially by AI" "The virtue signalers for being anti AI..never let them forget it bc they were the ones that were trying to go around and force everybody into thinking some type of technology wasn't the future..all for appearances" (Via AsmonTV on YT)

Asmongold says to never forget the anti AI people in video about AI & GPT-6 Astra "If you're not using these tools and other people are, they're gonna beat you and then people are gonna choose the winner..think about how many things now are determined or done partially by AI" "The virtue signalers for being anti AI..never let them forget it bc they were the ones that were trying to go around and force everybody into thinking some type of technology wasn't the future..all for appearances" (Via AsmonTV on YT)

yeet

25,340 Aufrufe • vor 6 Stunden

I can't believe this worked! I saw the new poster for Neuromancer and thought: "What a cool font! Can I recreate it with AI?" I went to ChatGPT using GPT-6 Astra, and I gave the poster and this prompt: "Create a full font similar to the one in the attached poster, and animate a showcase presentation for the font using the Higgsfield plugin" It even did two versions of the font: Regular and Signal Fully usable, perfectly working fonts. It took 13m 19s to make all of this.

I can't believe this worked! I saw the new poster for Neuromancer and thought: "What a cool font! Can I recreate it with AI?" I went to ChatGPT using GPT-6 Astra, and I gave the poster and this prompt: "Create a full font similar to the one in the attached poster, and animate a showcase presentation for the font using the Higgsfield plugin" It even did two versions of the font: Regular and Signal Fully usable, perfectly working fonts. It took 13m 19s to make all of this.

Alex Patrascu

20,127 Aufrufe • vor 3 Tagen

I watched this video posted by a tourist in Zimbabwe who has been promoting Zimbabwean tourism on his journey across the country. My first instinct was to ask, what is this? There are times when we do not just have to criticise, but must look for solutions. I think this is not a tourism problem, it is a policing problem that affects tourism, and it is a problem that does not just affect tourists but Zimbabweans as well who are driving across the country. The solution, in my view, is straightforward. When tourists enter our country, at the point of the border, they should be required to purchase all the necessary road safety paraphernalia demanded by the Zimbabwean police. First of all, I do not understand why one needs four triangles. Triangles are meant for when your car breaks down, you place one at the back and one at the front, that is two triangles. This tourist had three, yet he was told he needed four. I do not know why he needed four. But even if, for argument’s sake, he needed a hundred, then tell him at the border that he needs a hundred, and that there is a shop there selling them, even if it is a government-run shop. Make it a requirement that no motorist drives out of the border clearing area without the required triangles. They must buy them there and then. When they get to the exit gate, at that final clearing bay, they show the triangles and proceed, so that they do not encounter problems on the roads. If this is not done, you create situations like this one, where the Ministry of Tourism is dragged into an issue that has nothing to do with it, yet its work ends up being affected because of the ineffectiveness and lack of coordination among different government agencies. The requirement for triangles falls under the Ministry of Home Affairs, which superintends the police, so it must ensure that before any vehicle is cleared to leave the border, it complies. In most countries, you do not need four triangles. I have seen this absurdity in Zimbabwe only, and I experienced it. I own a car which has inbuilt reflectors, factory-fitted safety reflectors that perform the same function. Yet when you get to a Zimbabwean roadblock, they still want to see a separate portable reflector, even though the inbuilt system does the same job. This is a breakdown of common sense, and it does not just affect tourists, it affects Zimbabweans too. So instead of simply criticising, I chose to offer a solution. The responsible government agency and ministry must make it a requirement that any motorist entering the country has the stipulated triangles before they are cleared to leave the border. And if they do not have the four triangles, as required, as ridiculous as it sounds, there must be a facility at the border where they can purchase them and then proceed with their journey without harassment.

I watched this video posted by a tourist in Zimbabwe who has been promoting Zimbabwean tourism on his journey across the country. My first instinct was to ask, what is this? There are times when we do not just have to criticise, but must look for solutions. I think this is not a tourism problem, it is a policing problem that affects tourism, and it is a problem that does not just affect tourists but Zimbabweans as well who are driving across the country. The solution, in my view, is straightforward. When tourists enter our country, at the point of the border, they should be required to purchase all the necessary road safety paraphernalia demanded by the Zimbabwean police. First of all, I do not understand why one needs four triangles. Triangles are meant for when your car breaks down, you place one at the back and one at the front, that is two triangles. This tourist had three, yet he was told he needed four. I do not know why he needed four. But even if, for argument’s sake, he needed a hundred, then tell him at the border that he needs a hundred, and that there is a shop there selling them, even if it is a government-run shop. Make it a requirement that no motorist drives out of the border clearing area without the required triangles. They must buy them there and then. When they get to the exit gate, at that final clearing bay, they show the triangles and proceed, so that they do not encounter problems on the roads. If this is not done, you create situations like this one, where the Ministry of Tourism is dragged into an issue that has nothing to do with it, yet its work ends up being affected because of the ineffectiveness and lack of coordination among different government agencies. The requirement for triangles falls under the Ministry of Home Affairs, which superintends the police, so it must ensure that before any vehicle is cleared to leave the border, it complies. In most countries, you do not need four triangles. I have seen this absurdity in Zimbabwe only, and I experienced it. I own a car which has inbuilt reflectors, factory-fitted safety reflectors that perform the same function. Yet when you get to a Zimbabwean roadblock, they still want to see a separate portable reflector, even though the inbuilt system does the same job. This is a breakdown of common sense, and it does not just affect tourists, it affects Zimbabweans too. So instead of simply criticising, I chose to offer a solution. The responsible government agency and ministry must make it a requirement that any motorist entering the country has the stipulated triangles before they are cleared to leave the border. And if they do not have the four triangles, as required, as ridiculous as it sounds, there must be a facility at the border where they can purchase them and then proceed with their journey without harassment.

Hopewell Chin’ono

88,554 Aufrufe • vor 7 Monaten

Gave Astra a 3D scan of my parents old home to make it an editable scene. Then I turned down gravity and opened a portal. Turns out multimodal LLMs might have crossed the chasm on inverse graphics. Tremendous implications for everything from VFX and AR/VR to robotics. Process: ~400 2D photos I took in 2019 went through RealityScan and became a photogrammetry mesh. That’s the classical reconstruction step. Then I dropped that mesh into Blender and used Astra to turn it into a fully editable, cleaned up 3D scene. Asked it to use textures from my photo scan and create procedural 3D shaders for the rest. It's good but it’s definitely not perfect -- funny thing is some of the mistakes are inherited from the reference mesh RealityScan produced i.e. the bird statue’s legs, contours of the furniture etc. This is where humans still have much better “spatial autocomplete” and can take an output like this all the way. My next step will be to see if I can let it use CUA with the photoscan software to interactively reference the source pixel imagery and refine its work in Blender and get even closer to reality.

Gave Astra a 3D scan of my parents old home to make it an editable scene. Then I turned down gravity and opened a portal. Turns out multimodal LLMs might have crossed the chasm on inverse graphics. Tremendous implications for everything from VFX and AR/VR to robotics. Process: ~400 2D photos I took in 2019 went through RealityScan and became a photogrammetry mesh. That’s the classical reconstruction step. Then I dropped that mesh into Blender and used Astra to turn it into a fully editable, cleaned up 3D scene. Asked it to use textures from my photo scan and create procedural 3D shaders for the rest. It's good but it’s definitely not perfect -- funny thing is some of the mistakes are inherited from the reference mesh RealityScan produced i.e. the bird statue’s legs, contours of the furniture etc. This is where humans still have much better “spatial autocomplete” and can take an output like this all the way. My next step will be to see if I can let it use CUA with the photoscan software to interactively reference the source pixel imagery and refine its work in Blender and get even closer to reality.

Bilawal Sidhu

49,885 Aufrufe • vor 5 Tagen

I used to think the biggest promise of AI video was making production faster. Now I’m wondering if the bigger change is making pre-production accessible to more people. You can think through a scene spatially with GPT-6 Astra, establish camera and character movement, bring that scene into CapCut PC, generate with Seedance 2.5, and then keep refining the actual sequence. That creates an interesting possibility: What if creators who never had access to a traditional production team can start thinking like directors before they ever press “generate”? AI might not just be changing how we make footage. It might be changing who gets to plan a film. #GPT6Astra #CapCutPC #AIVideo #Seedance25

I used to think the biggest promise of AI video was making production faster. Now I’m wondering if the bigger change is making pre-production accessible to more people. You can think through a scene spatially with GPT-6 Astra, establish camera and character movement, bring that scene into CapCut PC, generate with Seedance 2.5, and then keep refining the actual sequence. That creates an interesting possibility: What if creators who never had access to a traditional production team can start thinking like directors before they ever press “generate”? AI might not just be changing how we make footage. It might be changing who gets to plan a film. #GPT6Astra #CapCutPC #AIVideo #Seedance25

Mushfiq Sajib

39,023 Aufrufe • vor 3 Tagen

Let's build the next character for the team! I’m continuing to test the modular character setup in UEFN using the Metahuman Component. Works really well with custom NPCs! For this new character, I'm back to a fresh 3D workflow using AssetHub . Still aiming for that flat/ anime style so I can go straight to the Tripo P1 model and get the low poly textured meshes to work with. Assembling and rigging are done in Blender. Again making a shape key for the eyes blinking. Because I'm going to use the same bone structure, I can re-use some Control Rig systems like the hair and eyes procedural animations. The character has 35K triangles and each accessory is about 2.5K.

Let's build the next character for the team! I’m continuing to test the modular character setup in UEFN using the Metahuman Component. Works really well with custom NPCs! For this new character, I'm back to a fresh 3D workflow using AssetHub . Still aiming for that flat/ anime style so I can go straight to the Tripo P1 model and get the low poly textured meshes to work with. Assembling and rigging are done in Blender. Again making a shape key for the eyes blinking. Because I'm going to use the same bone structure, I can re-use some Control Rig systems like the hair and eyes procedural animations. The character has 35K triangles and each accessory is about 2.5K.

Jerome | InsaneUnreal

16,578 Aufrufe • vor 3 Monaten

Here's a little demo I made in Spline v2 using the new AI Agent Mode. This is in the editor, in preview mode. You can try it too, I just gave it this prompt: "Create a cloth simulation and make it interact with this sphere. Let me move the sphere around and grab the cloth. Add a floor and some obstacles." The code can update the geometry of any object in the scene, and play with vertices and normals. I'd love to see what you can create with Spline. Let's go!! 🚀

Here's a little demo I made in Spline v2 using the new AI Agent Mode. This is in the editor, in preview mode. You can try it too, I just gave it this prompt: "Create a cloth simulation and make it interact with this sphere. Let me move the sphere around and grab the cloth. Add a floor and some obstacles." The code can update the geometry of any object in the scene, and play with vertices and normals. I'd love to see what you can create with Spline. Let's go!! 🚀

Joseph Azar

21,398 Aufrufe • vor 21 Tagen

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

Peter Gostev (SF 24-28 August)

257,389 Aufrufe • vor 6 Monaten

GPT-6 Astra is changing the way I edit by making every step before the final creative decision faster. The most productive AI editing workflow is not prompt to finished video; it’s prompt to editable asset, followed by refinement in CapCut PC. GPT-6 Astra can generate the intermediate files: a custom .cube LUT for a very specific color look, or an .srt file with customized animated subtitle effects ready to bring into the project. Then CapCut PC takes over the creative part. The LUT can be adjusted against the footage. The SRT can be dropped onto the timeline and edited across tracks. Edit Pilot, AI Edit and AI Extend can continue helping with post-production. And if the result isn’t right, the loop goes back to Astra. Generate → edit → refine → generate again. The real productivity gain isn’t letting AI finish the video. It’s making every step before the final decision faster. #GPT6Astra #CapCutPC #AIVideo #Seedance25

GPT-6 Astra is changing the way I edit by making every step before the final creative decision faster. The most productive AI editing workflow is not prompt to finished video; it’s prompt to editable asset, followed by refinement in CapCut PC. GPT-6 Astra can generate the intermediate files: a custom .cube LUT for a very specific color look, or an .srt file with customized animated subtitle effects ready to bring into the project. Then CapCut PC takes over the creative part. The LUT can be adjusted against the footage. The SRT can be dropped onto the timeline and edited across tracks. Edit Pilot, AI Edit and AI Extend can continue helping with post-production. And if the result isn’t right, the loop goes back to Astra. Generate → edit → refine → generate again. The real productivity gain isn’t letting AI finish the video. It’s making every step before the final decision faster. #GPT6Astra #CapCutPC #AIVideo #Seedance25

Ricardo Momo

49,346 Aufrufe • vor 1 Tag

I plugged ChatGPT Luna 5.6 and Claude Opus 5 into Blender through MCP, and one of them is one-shotting entire 3D scenes now. Top is Luna 5.6 in fast mode modeling ship cannons with a firing animation. Watching the scene grow mesh by mesh in real time is a separate kind of dopamine. Bottom is Opus 5 building a full carriage scene with terrain, rocks and lighting. This one is simply built for 3D -- the whole thing from a single prompt with zero retries and zero corrections. The entire bridge is one open-source repo, no Python and no modeling skills required: > The repo is with 16.9k stars under MIT license. > It works with any model -- Claude, GPT, Cursor, any MCP client. > The model sees your scene through a live socket and edits it in real time. A year ago this workflow didn't exist, and now the gap between an idea and a rendered 3D scene is one prompt. Save this one -- you will come back for the repo ↓

I plugged ChatGPT Luna 5.6 and Claude Opus 5 into Blender through MCP, and one of them is one-shotting entire 3D scenes now. Top is Luna 5.6 in fast mode modeling ship cannons with a firing animation. Watching the scene grow mesh by mesh in real time is a separate kind of dopamine. Bottom is Opus 5 building a full carriage scene with terrain, rocks and lighting. This one is simply built for 3D -- the whole thing from a single prompt with zero retries and zero corrections. The entire bridge is one open-source repo, no Python and no modeling skills required: > The repo is with 16.9k stars under MIT license. > It works with any model -- Claude, GPT, Cursor, any MCP client. > The model sees your scene through a live socket and edits it in real time. A year ago this workflow didn't exist, and now the gap between an idea and a rendered 3D scene is one prompt. Save this one -- you will come back for the repo ↓

slash1s

150,102 Aufrufe • vor 1 Monat

OiiOii AI is like Nano Banana but for Videos !! 🚨 Most AI video tools limit you to pre-made templates But I just turned a social media trend into a reusable AI workflow !! I created this in just 10 minutes using OiiOii AI's new Skill Maker feature to replace "Ronaldo" with "Sundar Pichai" I uploaded the reference video.... And OiiOii extracted the EXACT style, pacing & structure OiiOii AI is the ultimate shortcut to catch up with viral trends while keeping your content 100% original and unique. Its also 100% copyright-safe content 🙌 Try now with "FREE" AI Credits👇 Join the Discord: #AIAnimation #OiiOii

OiiOii AI is like Nano Banana but for Videos !! 🚨 Most AI video tools limit you to pre-made templates But I just turned a social media trend into a reusable AI workflow !! I created this in just 10 minutes using OiiOii AI's new Skill Maker feature to replace "Ronaldo" with "Sundar Pichai" I uploaded the reference video.... And OiiOii extracted the EXACT style, pacing & structure OiiOii AI is the ultimate shortcut to catch up with viral trends while keeping your content 100% original and unique. Its also 100% copyright-safe content 🙌 Try now with "FREE" AI Credits👇 Join the Discord: #AIAnimation #OiiOii

COLAW

131,265 Aufrufe • vor 1 Monat